Codex keeps adding useful features to their coding assistant, which I’m glad for because I like competition. Cool stuff!
Much like OpenClaw (the first to make a big splash way back in the dark ages of AI, January 2026), Hermes Agent can do all that and more with added benefits including but not limited to: 100% free; lives anywhere you want (on your main computer, on a laptop, on a VPS, etc.), not restricted to OpenAI’s garden.
Hermes Agent was designed/built from the ground-up to be self-improving/learning agent-first and easy to create persistent parallel agents (that run 24/7 when you want). After using Hermes for a couple months, I wondered, “Can I make the leap from using a coding assistant for my software dev TO setting up some agents in Hermes focused on software dev and point them at the projects?”
Five or so weeks in and the answer is YES! Hermes’ built-in “learning” and “memory” (that Codex is only just now starting to add in a semi-clunky way) makes a huge difference. I now have 14 agents (called “profiles” in Hermes) running in my Hermes. Each one has access to specific skills and knowledge/memories/learnings in order to best do its tasks. Some of those agents “own” a project. I talk to them in various ways, including through Telegram messenger! Imagine managing your software development from your phone!
Codex was designed/built to be a coding assistant, with persistent parallel agents and memory bolted on as an afterthought. Anthropic is doing the same thing with their Claude Code/CoWork but slightly behind OpenAI and more restrictive.
Hermes Agent goes even further. Want different kinds of memory? SQL-based, vector-embeddings? Markdown only? A mix? You have full control.
Watch the animated musical story / prediction of where things could be going and how we get there. Trigger warning: Short version skips past the dark times. Longer version tells the whole story.
